Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4528 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6330. Min Range: -7.6330
Max Act: 7.6330. Min Act: -0.1700
Data Index: 3455112 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6330. Min Range: -7.6330
Max Act: 7.5705. Min Act: -0.1700
Data Index: 5843661 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6330. Min Range: -7.6330
Max Act: 7.5393. Min Act: -0.1700
Data Index: 6913299 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6330. Min Range: -7.6330
Max Act: 7.4768. Min Act: -0.1700
Data Index: 8795767 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6330. Min Range: -7.6330
Max Act: 7.4768. Min Act: -0.1700
Data Index: 195770 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6330. Min Range: -7.6330
Max Act: 7.4768. Min Act: -0.1700
Data Index: 8367242 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6330. Min Range: -7.6330
Max Act: 7.4768. Min Act: -0.1700
Data Index: 5681234 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6330. Min Range: -7.6330
Max Act: 7.3830. Min Act: -0.1700
Data Index: 2447237 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6330. Min Range: -7.6330
Max Act: 7.3830. Min Act: -0.1700
Data Index: 5606931 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6330. Min Range: -7.6330
Max Act: 7.3830. Min Act: -0.1700
Data Index: 2742735 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6330. Min Range: -7.6330
Max Act: 7.3518. Min Act: -0.1700
Data Index: 6098907 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6330. Min Range: -7.6330
Max Act: 7.3518. Min Act: -0.1700
Data Index: 4508645 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6330. Min Range: -7.6330
Max Act: 7.3518. Min Act: -0.1700
Data Index: 5486670 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6330. Min Range: -7.6330
Max Act: 7.3205. Min Act: -0.1700
Data Index: 6963068 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6330. Min Range: -7.6330
Max Act: 7.3205. Min Act: -0.1700
Data Index: 901053 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6330. Min Range: -7.6330
Max Act: 7.3205. Min Act: -0.1700
Data Index: 8380896 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6330. Min Range: -7.6330
Max Act: 7.3205. Min Act: -0.1700
Data Index: 46309 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6330. Min Range: -7.6330
Max Act: 7.2893. Min Act: -0.1700
Data Index: 7811462 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6330. Min Range: -7.6330
Max Act: 7.2893. Min Act: -0.1700
Data Index: 2325648 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6330. Min Range: -7.6330
Max Act: 7.2893. Min Act: -0.1700
Data Index: 3752800 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19